Convolutional Neural Network-Based Clinical Predictors of Oral Dysplasia: Class Activation Map Analysis of Deep Learning Results
Authors:
- Seda CamalanSCSeda Camalan
- Hanya MahmoodHanya Mahmood
- Hamidullah BinolHBHamidullah Binol
- Anna Luiza Damaceno AraújoAAAnna Luiza Damaceno Araújo
- Alan Roger Santos-SilvaAlan Roger Santos-Silva
- Pablo Agustin VargasPablo Agustin Vargas
- Marcio Ajudarte LopesMLMarcio Ajudarte Lopes
- Syed Ali KhurramSKSyed Ali Khurram
- Metin N. GurcanMetin N. Gurcan
Open Access
Abstract
Oral cancer/oral squamous cell carcinoma is among the top ten most common cancers globally, with over 500,000 new cases and 350,000 associated deaths every year worldwide. There is a critical need for objective, novel technologies that facilitate early, accurate diagnosis. For this purpose, we have developed a method to classify images as “suspicious” and “normal” by performing transfer learning on Inception-ResNet-V2 and generated automated heat maps to highlight the region of the images most likely to be involved in decision making. We have tested the developed method’s feasibility on two independent datasets of clinical photographic images of 30 and 24 patients from the UK and Brazil, respectively. Both 10-fold cross-validation and leave-one-patient-out validation methods were performed to test the system, achieving accuracies of 73.6% (±19%) and 90.9% (±12%), F1-scores of 97.9% and 87.2%, and precision values of 95.4% and 99.3% at recall values of 100.0% and 81.1% on these two respective cohorts. This study presents several novel findings and approaches, namely the development and validation of our methods on two datasets collected in different countries showing that using patches instead of the whole lesion image leads to better performance and analyzing which regions of the images are predictive of the classes using class activation map analysis.Keywords
This publication has 40 references indexed in Scilit:
- Deep Residual Learning for Image Recognition2016
- Learning Deep Features for Discriminative Localization2016
- Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural NetworksIEEE Transactions on Medical Imaging, 2016
- Malignant transformation of oral leukoplakia: a systematic review of observational studiesJournal of Oral Pathology & Medicine, 2015
- Diagnostic tests for oral cancer and potentially malignant disorders in patients presenting with clinically evident lesionsCochrane Database of Systematic Reviews, 2015
- Machine learning, medical diagnosis, and biomedical engineering research - commentaryBioMedical Engineering OnLine, 2014
- A retrospective analysis of clinical features of oral malignant and potentially malignant disorders with and without oral epithelial dysplasiaOral Surgery, Oral Medicine, Oral Pathology and Oral Radiology, 2013
- The limitations of the clinical oral examination in detecting dysplastic oral lesions and oral squamous cell carcinomaThe Journal of the American Dental Association, 2012
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Critical evaluation of diagnostic aids for the detection of oral cancerOral Oncology, 2008